Medical-Llama3-8B: benchmark results

Provider: Other. Released 2024-05-01. Access: Open.

Unified ELO 1478 ± 15, rank #1478 of 2928 rated models, from 17 benchmark results.

Strongest benchmark results

BenchmarkScoreMetricPercentile
Open Medical LLM - MMLU Anatomy68.89Accuracy (%)83.5
Open LLM Leaderboard v1 - MMLU65.12Accuracy (%) (5-shot)82
Open LLM Leaderboard v1 - WinoGrande77.74Accuracy (%) (5-shot)58.2
Open LLM Leaderboard v1 - GSM8K40.49Accuracy (%) (5-shot)55.9
Open Medical LLM - MedMCQA53.65Accuracy (%)54.5
Open Medical LLM - MedQA (USMLE)56.56Accuracy (%)54.5
Open Medical LLM66.95Average Accuracy (%)53.4
Open Medical LLM - MMLU College Biology74.31Accuracy (%)52.8
Open Medical-LLM Leaderboard66.95Medical average (%)52.2
Open Medical LLM - PubMedQA74Accuracy (%)51.1
Open Medical LLM - MMLU Medical Genetics75Accuracy (%)50.9
Open Medical LLM - MMLU Clinical Knowledge70.94Accuracy (%)50.3

Interactive version: theaggregate.ai/model?slug=medical-llama3-8b · How It Works · Data refreshed daily, snapshot 2026-09-23.